{"total":168,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196,"area":null},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181,"area":null},{"id":"2207.01405","title":"I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference","created":"2022-07-04","cited_by_count":95,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64,"area":null},{"id":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2306.00317","title":"FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization","created":"2023-06-01","cited_by_count":48,"area":null},{"id":"2307.09782","title":"ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats","created":"2023-07-19","cited_by_count":44,"area":null},{"id":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","cited_by_count":36,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2405.03144","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","created":"2024-05-06","cited_by_count":32,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2105.03536","title":"Pareto-Optimal Quantized ResNet Is Mostly 4-bit","created":"2021-05-07","cited_by_count":26,"area":null},{"id":"2206.06501","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","created":"2022-06-13","cited_by_count":26,"area":null},{"id":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","cited_by_count":20,"area":null},{"id":"2305.12356","title":"Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models","created":"2023-05-21","cited_by_count":19,"area":null},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2308.15987","title":"FPTQ: Fine-grained Post-Training Quantization for Large Language Models","created":"2023-08-30","cited_by_count":16,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2410.05437","title":"ESPACE: Dimensionality Reduction of Activations for Model Compression","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2505.17604","title":"Adaptive Semantic Token Communication for Transformer-based Edge Inference","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2302.12480","title":"Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?","created":"2023-02-24","cited_by_count":13,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2106.16006","title":"Improving the Efficiency of Transformers for Resource-Constrained Devices","created":"2021-06-30","cited_by_count":12,"area":null},{"id":"2102.09337","title":"Reinforcement Learning for Datacenter Congestion Control","created":"2021-02-18","cited_by_count":11,"area":null},{"id":"2109.09113","title":"HPTQ: Hardware-Friendly Post Training Quantization","created":"2021-09-19","cited_by_count":10,"area":null},{"id":"2211.02854","title":"Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2311.09550","title":"A Speed Odyssey for Deployable Quantization of LLMs","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2405.02330","title":"Adaptive Semantic Token Selection for AI-native Goal-oriented Communications","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2406.09477","title":"Q-S5: Towards Quantized State Space Models","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2508.01506","title":"FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models","created":"2025-08-02","cited_by_count":9,"area":null},{"id":"2108.08166","title":"Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization","created":"2021-08-18","cited_by_count":8,"area":null},{"id":"2108.12074","title":"4-bit Quantization of LSTM-based Speech Recognition Models","created":"2021-08-27","cited_by_count":8,"area":null},{"id":"2503.16709","title":"QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge","created":"2025-03-20","cited_by_count":8,"area":null},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7,"area":null},{"id":"2106.13914","title":"LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","created":"2021-06-26","cited_by_count":7,"area":null},{"id":"2110.08271","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","created":"2021-10-15","cited_by_count":7,"area":null},{"id":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2405.13938","title":"eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2411.11038","title":"EfQAT: An Efficient Framework for Quantization-Aware Training","created":"2024-11-17","cited_by_count":7,"area":null},{"id":"2502.05376","title":"LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2103.10142","title":"Reduced Precision Strategies for Deep Learning: A High Energy Physics Generative Adversarial Network Use Case","created":"2021-03-18","cited_by_count":6,"area":null},{"id":"2109.00810","title":"Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse","created":"2021-09-02","cited_by_count":6,"area":null},{"id":"2202.05048","title":"Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment","created":"2022-02-10","cited_by_count":6,"area":null},{"id":"2203.05492","title":"An Empirical Study of Low Precision Quantization for TinyML","created":"2022-03-10","cited_by_count":6,"area":null},{"id":"2303.12557","title":"Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems","created":"2023-03-22","cited_by_count":6,"area":null},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2312.10588","title":"Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting","created":"2023-12-17","cited_by_count":6,"area":null},{"id":"2409.17092","title":"Accumulator-Aware Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2312.03788","title":"SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2401.10432","title":"A2Q+: Improving Accumulator-Aware Weight Quantization","created":"2024-01-19","cited_by_count":5,"area":null},{"id":"2404.19288","title":"Training-free Graph Neural Networks and the Power of Labels as Features","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2409.14330","title":"Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2510.17189","title":"SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2105.13890","title":"Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization","created":"2021-05-27","cited_by_count":4,"area":null},{"id":"2205.06287","title":"Adaptive Block Floating-Point for Analog Deep Learning Hardware","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2210.15623","title":"Neural Networks with Quantization Constraints","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2301.01651","title":"On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats","created":"2023-01-04","cited_by_count":4,"area":null},{"id":"2312.05725","title":"FP8-BERT: Post-Training Quantization for Transformer","created":"2023-12-10","cited_by_count":4,"area":null},{"id":"2402.02043","title":"A Plug-in Tiny AI Module for Intelligent and Selective Sensor Data Transmission","created":"2024-02-03","cited_by_count":4,"area":null},{"id":"2505.04861","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2206.11062","title":"Answer Fast: Accelerating BERT on the Tensor Streaming Processor","created":"2022-06-22","cited_by_count":3,"area":null},{"id":"2207.06282","title":"DiverGet: A Search-Based Software Testing Approach for Deep Neural Network Quantization Assessment","created":"2022-07-13","cited_by_count":3,"area":null},{"id":"2208.00338","title":"Symmetry Regularization and Saturating Nonlinearity for Robust Quantization","created":"2022-07-31","cited_by_count":3,"area":null},{"id":"2210.15016","title":"TPU-MLIR: A Compiler For TPU Using MLIR","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2212.02634","title":"QFT: Post-training quantization via fast joint finetuning of all degrees of freedom","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2302.01382","title":"Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2306.04879","title":"Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2401.07598","title":"MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2401.17269","title":"Effect of Weight Quantization on Learning Models by Typical Case Analysis","created":"2024-01-30","cited_by_count":3,"area":null},{"id":"2403.17154","title":"On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2404.15781","title":"Real-Time Compressed Sensing for Joint Hyperspectral Image Transmission and Restoration for CubeSat","created":"2024-04-24","cited_by_count":3,"area":null},{"id":"2408.09209","title":"H2PIPE: High throughput CNN Inference on FPGAs with High-Bandwidth Memory","created":"2024-08-17","cited_by_count":3,"area":null},{"id":"2502.01330","title":"Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2504.14915","title":"StableQuant: Layer Adaptive Post-Training Quantization for Speech Foundation Models","created":"2025-04-21","cited_by_count":3,"area":null},{"id":"2110.02911","title":"Shifting Capsule Networks from the Cloud to the Deep Edge","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2206.07882","title":"Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2206.12794","title":"CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps","created":"2022-06-26","cited_by_count":2,"area":null},{"id":"2207.02295","title":"Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2307.11904","title":"Model Compression Methods for YOLOv5: A Review","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2311.07625","title":"Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2311.17323","title":"Mirage: An RNS-Based Photonic Accelerator for DNN Training","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2405.00966","title":"Efficient Compression of Multitask Multilingual Speech Models","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2407.08272","title":"PowerYOLO: Mixed Precision Model for Hardware Efficient Object Detection with Event Data","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2408.03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2503.06183","title":"Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2503.14932","title":"Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices","created":"2025-03-19","cited_by_count":2,"area":null}],"next_cursor":"100"}